© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26225
    Prev
    Next
    INDEX
    Explanations

    some followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     some
    -0.16
     SOME
    -0.12
    some
    -0.11
     WHATSOEVER
    -0.09
     whatsoever
    -0.09
    "Some
    -0.09
     somewhat
    -0.09
     somewhere
    -0.09
     somehow
    -0.09
     Some
    -0.09
    POSITIVE LOGITS
    place
    0.34
    ones
    0.29
    /all
    0.28
    hw
    0.23
    body
    0.22
    how
    0.21
    kind
    0.21
    ht
    0.20
    pon
    0.19
     sort
    0.18
    Activations Density 0.098%

    No Known Activations